欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
提出了一种基于支持向量机的InSAR干涉图区域分割相位解缠法,以支持向量机为分类工具,利用干涉图中的残差点、相位导数方差等相位属性对干涉图中像元分类,把干涉图分割成高质量非掩模区域和低质量掩模区域。先用改进的Itoh方法对非掩模区域解缠,然后应用区域生长策略对掩模区域解缠。最后用真实的和模拟的干涉相位图试验表明算法比现有的传统算法如枝切法等InSAR干涉图相位解缠方法更有效。
英文摘要：
A region-cutting phase unwrapping algorithm based on SVM （Support Vector Machines） is proposed, and every pixel can be classified using the phase-related information including residue and phase derivate variance, thus the intetferogram is cut into high-quality non-mask region and low-quality mask region. Region-growing strategy is applied to unwrap mask region after the non-mask region is unwrapped by modified ltoh method, The experiment result on real and simulated SAR interferogram shows the proposed algorithm is more effective than some existing algorithms such as the branch-cut algorithm.
同期刊论文项目
同项目期刊论文
期刊信息
位置：